Modeling of Optimized Data Processing Framework for Potential Knowledge Discovery And Recommendation Based on Healthcare Big Data
Karunamurthy A1, M.Aramudhan2
1Karunamurthy A, Research Scholar, Department of Computer Science, Research and Development Centre, Bharathiar University, Coimbatore (Tamil Nadu), India.
2Dr. M. Aramudhan, Associate Professor & Head, Department of Information Technology, Perunthalaivar Kamarajar Institute of Engineering & Technology, (Karaikal), India.
Manuscript received on 07 March 2019 | Revised Manuscript received on 20 March 2019 | Manuscript published on 30 March 2019 | PP: 1193-1198 | Volume-8 Issue-5, March 2019 | Retrieval Number: E3099038519/19©BEIESP
Open Access | Ethics and Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: The growth of data in healthcare application provides voluminous information about patients which are rich and meaningful insights using machine learning algorithms. In such cases, the volume and velocity of such high dimensional data requires new big data analytics framework where conventional machine learning tools cannot be directly applied. To overcome the issues like data uncertainty and misclassified data, we propose a better recommendation and optimization model which facilitates the healthcare systems. The proposed study is enhanced for data processing framework and better decision support systems. The proposed MR- FA devises the storage system of the big data which effectively generates the index for the received data. It works like partition based clustering algorithms which splits and then stores the given data to achieve the transactional database. Then, k-NN machine learning model is applied over transactional database to derive relevant knowledge using different k-values. It helps us to achieve suggest the knowledge for the users. The proposed framework is analyzed on four datasets collected from UCI machine repository. The performance metrics such as parallel processing time and reliability time are studied. It states that the computation of optimal fitness values helps the system to achieve the desired goal better parallel processing time with efficient reliability time.
Keyword: Healthcare Systems, Uncertainty, Decision Support Systems, Recommendation Systems, Machine Learning Models, Transactional Database and the Reliability.
Scope of the Article: Machine Learning